© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196127
    Prev
    Next
    INDEX
    Explanations

    Please

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diligently
    0.46
     cuidad
    0.43
    宍
    0.42
     babys
    0.40
     watchful
    0.39
     analysed
    0.39
     tranquilo
    0.39
     tweaks
    0.38
     hả
    0.38
     studied
    0.38
    POSITIVE LOGITS
    하면서
    0.42
     fed
    0.40
    while
    0.39
    fed
    0.38
    vrage
    0.38
    瓣
    0.37
     mentre
    0.36
     ενώ
    0.36
    shaped
    0.35
     Gloss
    0.35
    Activations Density 0.003%

    No Known Activations